Workshops

LATIS offers a series of workshops that are free and open to all faculty and graduate students. Join our LATIS Research Workshops Google Group to be the first to learn about workshops. You can view the slides and materials from past workshops at the LATIS Workshop Materials website.

 

Spring 2021 Workshops

(Detailed descriptions and registration info coming soon)

 

Synchronous workshops

These workshops will be in the same format as Fall 2020, and will be held on Fridays from 10am-noon via Zoom, unless otherwise noted. 

Introduction to Nvivo on Mac - Jan 29 - Registration

Introduction to Nvivo on Windows- Feb 5 - Registration

Advanced Nvivo - Feb 12 - Registration

Computational Text Analysis -March 5 - Registration

Data Management when you graduate - April 7 (Wed.) - Registration

 

Asynchronous workshops with live Q&A session 

The content for these workshops will be completed asynchronously. Each will have a scheduled live Q&A session held Wednesdays 10am-noon via Zoom. Participants can ask questions about the workshop content or their own research work in the tools. 

Qualtrics - Jan 12 (Tue.) open Q&A  (10am - 12pm)  - Registration

Qualtrics - Feb 3 open Q&A  (10am - 12pm)  - Registration

Introduction to Survey Sampling - Available Feb 8 - Registration

Intro to Python - March 3  open Q&A  (10am - 12pm) - Registration

 

Combination asynchronous & synchronous workshops 

These workshops will consist of both asynchronous content and synchronous demonstrations. Workshops will be held on Fridays from 1:30-3pm via Zoom. 

Working with Qualtrics data in R - Feb 5 - Registration

Reshaping data in R - Feb 12 - Registration

Create a table using dplyr in R - Feb 26 - Registration

Publication worthy graphs with ggplot2 in R - March 19 - Registration

R Markdown - March 26 - Registration

 

Workshop descriptions

 

LATIS Qualtrics Tutorials 

Qualtrics is a versatile data collection tool that is available to all University researchers, and it can be used for a wide range of survey and experimental needs. This series of asynchronous tutorials are on Canvas, and we will have a 2-hour Zoom open Q&A “hour” with LATIS’ Survey Methodologist and Project Designer on 1/12 and 2/3 (10am-12pm) for those wishing to discuss any tutorial content, or other Qualtrics questions, in person. All tutorial content is self-paced. 

  1. Introduction to Qualtrics: Are you brand new to using Qualtrics? Or has it been a really long time since you used Qualtrics? Start here to learn the ropes.
  2. Qualtrics Data Integrity & Management: No matter if you are new to Qualtrics or a long-time user, this module is a must for any Qualtrics user who is interested in 1) how to make Qualtrics data more readable and suitable to their needs, 2) best practices for conducting reproducible research within Qualtrics (e.g., sharing and archiving survey information, how to export data reproducibly, etc.). 
  3. Qualtrics Experimental Design: Sometimes figuring out the right bells and whistles for more complex research designs in Qualtrics can be daunting. If you’re looking to build complex surveys or experimental tasks within Qualtrics, this tutorial is for you! We cover how to use some more complex functionality within Qualtrics, such as the using the survey flow, branching logic, embedded data, embedded media, piped text, “loop & merge”, integration with MTurk/Prolific, and more! 

 

Introduction to Python for Social Science

Python has seen wide adoption in academic research because it is a powerful but easy-to-learn programming language. It can be used in a manner similar to R or Stata for statistical processing, but also provides wider application in data processing, collection, and file management. Python is free and can be used in many phases of a project to enhance the reproducibility of research. This workshop will teach you how to get started using Python and some of its basic syntax, grammar and structures. It will also introduce the popular package Pandas which provides a familiar dataframe structure to import, format, and clean data as well as functions to manipulate, filter, and analyze data.

This workshop will cover how to:

  • Use Python 3 in a JupyterLab computing environment
  • Create an script (syntax/command file) to capture steps in a reproducible way
  • Use Python to grab data from a large number of files quickly
  • Load a comma-delimited spreadsheet (.csv) into Pandas as a dataframe
  • View and clean that data
  • Save cleaned data file in formats for later use

To be successful, you should have:

  • A familiarity with data used in the social sciences
  • A familiarity with another statistical or data processing tool, such as R, SPSS, Stata, SAS, or Excel
  • A computer that can run JupyterLab in an internet browser

 

Advanced NVivo

NVivo is a qualitative data management, coding and markup tool, that facilitates powerful querying and exploration of source materials for both mixed methods and qualitative analysis. The software is provided for faculty and graduate students of the College of Liberal Arts, College of Education and Human Development and the Humphrey School of Public Affairs. This workshop introduces the advanced functions of NVivo, with basic knowledge of NVivo recommended.

This workshop will cover

  • A brief review of adding and managing source materials and codes
  • Creating classifications & attributes (variables) with demographic data and importing them from Excel
  • Organizing materials into “cases” to facilitate comparison
  • Using “auto-coding” to segment transcripts and other structured text
  • Complex queries with codes and concepts subset by attributes, cases, or sources
  • Running the built-in interrater reliability metrics
  • Importing data from other software including Qualtrics, OneNote, and Zotero
  • Exporting frequencies and code counts to statistical packages

To be successful, you should

  • Have a basic understanding of qualitative research methods
  • Be familiar with NVivo’s interface and basic functions
  • Install NVivo from z.umn.edu/getNVivo prior to the session, or install a trial from QSR International’s website

 

Research workflows in R

R is a popular tool for data analysis and statistical computing, and is a great alternative to tools like SPSS, Stata, or Excel. R is designed for reproducible research and can be used for many parts of the research process besides statistical analysis. This series of short workshops will demonstrate powerful uses of R for data cleaning, visualization, and reporting. 

Each 1-hour workshop will build on asynchronous introductory material and will consist of a demonstration and Q&A. 

  1. Working with Qualtrics data in R: Qualtrics is a popular tool for survey research, but the resulting data often require cleaning before analyzing in R. Learn how to efficiently clean Qualtrics data for use in R, including how to reproducibly remove the multiple headers, save labels, and combine multi-response columns. 
  2. Reshaping data: Data are not always in the right format for analysis or visualization. Learn how to transform data from wide to long format and back again. 
  3. Create a table using dplyr: Learn how to aggregate data and create summaries for tables for publication. 
  4. Publication worthy graphs with ggplot2: Learn how to adjust colors, axises, legends, and themes, as well as how to reproducibility save graphs for publication. 
  5. R Markdown: Combine code, output, and text into readable documents with R Markdown. Learn how to create a basic R markdown document for research. 

 

 

Introduction to Computational Text Analysis

Scholars in humanities and social science fields are using computational tools to explore large corpora of digital texts. This hands-on workshop will introduce some common methods such as topic modeling and sentiment analysis, as well as fundamental cleaning and processing tasks for a text analysis workflow in Python.

This workshop will cover how to:

  • Read and write text files in Python
  • Manipulate ‘strings’ of text
  • Pre-process text for analysis (basic cleaning tasks such as normalizing case, stripping punctuation and whitespace, etc)
  • Count word frequencies
  • Create a document term matrix (a ‘bag of words’)
  • Build topic models and conduct sentiment analysis

This workshop will also briefly introduce concepts and tools related to other common computational text analysis tasks: regular expressions (regex) and text cleaning, string matching and fuzzy matching, NLTK tools such as named entity recognition and parts-of-speech tagging, word embeddings (word2vec), classification tasks (e.g., stylometry, genre identification…)

To be successful, you should have:

  • A familiarity with textual data used in the social sciences
  • An intro-level familiarity with Python 

For an online introduction to Python see the Fall 2019 LATIS Python workshop recording and materials or LinkedIn Learning’s Python Essentials

Optional: Install Python on your laptop (we recommend Anaconda).

There will be an online environment available for using Python, so local installation is not required.

 

Data Management in transition: Strategies for when you graduate

Research and creative work doesn't end with degree completion; however, access to many of the data storage tools and software that have supported that work changes when students become alumni. This workshop will help graduate students navigate questions about whether they can take their data and materials with them when they leave the university, and if so, how to do it. 

This workshop will cover:

  • The University policies that guide ownership of data
  • Access changes to storage, software, and services that happen upon graduation 
  • Strategies and tips for ensuring data are accessible and understandable long after graduation
  • How to make a plan to ensure a smooth transition for your data and materials between graduate school and your next endeavor

To be successful, you should:

  • Be a graduate student at the University of Minnesota at least a year into your program (it never hurts to plan early!), or who is nearing the end of your program. 
  • Have a research project (part of a dissertation or thesis) that has generated data or materials that you want to keep track of after you leave. This can include collaborative projects that will continue at UMN after graduation. 

 

Introduction to NVivo

NVivo is a qualitative data management, coding and markup tool, that facilitates powerful querying and exploration of source materials for both mixed methods and qualitative analysis. It integrates well with tools that assist in data collection and can handle a wide variety of source materials. This workshop introduces the basic functions of NVivo, with no prior experience necessary. Licensing is provided for faculty and graduate students of the College of Liberal Arts; others can run the software in trial-mode for two weeks or can be given temporary access to the software for this workshop. 

This workshop will cover

  • Adding your source materials (text, images, audio/video, survey/spreadsheets)
  • Working with concepts (or codes/tags) and their definitions
  • Making annotations and analytical memos
  • Using text queries to speed up coding
  • Finding patterns in the concepts identified in the source materials
  • Importing data from other tools including Qualtrics, OneNote, and Zotero
  • Exporting excerpts and making backups
  • Working in teams

To be successful, you should

  • Be familiar with source materials used in qualitative research (interviews, focus groups, field notes, archival documents, etc.)
  • Be familiar with the types of questions asked in qualitative research
  • Download and install NVivo from z.umn.edu/getNVivo prior to the workshop

 

Introduction to Survey Sampling 

This is an interactive, self-paced Canvas course, designed for those who are either 1) completely new to surveying or 2) have never had formal instruction in survey/sampling design. By the end of course, you should be able to: 

  1. Differentiate between a census and a sample

  2. Describe features and limitations of common sampling methods

  3. Recognize different sources of survey error/bias
  4. Describe how different sources of survey error/bias affects the conclusions you can draw with your survey
  5. Approach your own survey sampling in an ethical manner 

This brief, introductory course to sampling is designed to take around 1 hour to complete.

Click here to request access to our Introduction to Survey Sampling course. It will be made available on 2/8/2020.